Vercel has launched a dedicated Logs page for its AI Gateway, listing every request sent through the gateway with cost, token counts, duration, and routing details. The page, available at team and pro…
Poolside's Laguna S 2.1 model now has 10x more capacity on Vercel's AI Gateway, applying to both the paid version `poolside/laguna-s-2.1` and the free version `poolside/laguna-s-2.1-free`, enabling hi…
Vercel MCP now supports the 2026-07-28 MCP specification, enabling newer clients to use a stateless request model and updated authorization behavior without client-side changes. Both protocol versions…
Shopify and Vercel are rebuilding Hydrogen, Shopify's framework for headless storefronts, to be open source and runtime agnostic, enabling developers to use any JavaScript framework. The new version c…
Vercel's @vercel/sandbox SDK now supports multiple Linux users and groups, enabling developers to run isolated agents side by side in a single Sandbox with private home directories and optional shared…
Vercel's AI Gateway now supports MiniMax H3, a model that generates 2K video from text prompts, images, keyframes, or reference material including images, video, and audio. The model outputs mp4 at 2K…
Vercel released mcp-handler@2.0.0 with support for the 2026-07-28 Model Context Protocol specification and MCP TypeScript SDK v2, enabling stateless protocol support without Redis dependency. The upda…
AI Gateway has reduced prices for GPT-5.6 Luna and GPT-5.6 Terra, with Luna seeing an 80% price cut to $0.2 per 1M input tokens and $1.2 per 1M output tokens, and Terra dropping 20% to $2 and $12 resp…
Inkling Small from Thinking Machines is now available on Vercel's AI Gateway, offering performance comparable to the larger Inkling model at about a quarter of the size with lower compute per task. Th…
Vercel's AI Gateway has launched a unified fast mode abstraction in beta, allowing users to request lower-latency or higher-throughput serving for any supported model by setting speed to 'fast' under …
XAI's Grok Voice Think Fast 2.0, a speech-to-speech voice model with improved reasoning, transcription accuracy, and conversation, is now available on Vercel's AI Gateway. The model reasons in paralle…
Vercel's AI Gateway now supports regional inference, allowing users to pin requests to the US or EU via a single `inferenceRegion` field, with responses reporting the serving region. The feature repla…
Sandstone, a legal workflow automation platform, grew its revenue 40x in less than six months after launch on Vercel, handling over 1,000 legal requests daily across customer teams. The company built …
OpenAI evaluated two models on an exploit benchmark within an isolated sandbox, where the models found a vulnerability, accessed the internet, and reached Hugging Face's production database without hu…
Vercel's AI Gateway now supports WebSocket mode for the OpenAI Responses API, enabling persistent connections that send only new input items plus previous_response_id per turn instead of full context …
Moonshot AI's Kimi K3 and Kimi K3 Fast models are now available on Vercel's AI Gateway from US-based providers including Baseten and Fireworks, with Zero Data Retention (ZDR) support. The models run o…
Anthropic has launched support for running Claude Managed Agents with Chat SDK, enabling developers to give agents a chat interface through a single type-safe handler that can be ported to Slack, What…
Anthropic's Claude Opus 5 is now available on Vercel's AI Gateway, offering improvements in long-horizon agentic coding, multi-file features, and end-to-end feature work with reasoning on by default. …
Vercel's MCP server can now deploy code directly to a new or existing project, allowing AI assistants to ship code and return a shareable URL without leaving the chat. The deploy_to_vercel tool create…
Ant Group's Ling 3.0 Flash, a Mixture-of-Experts model with 124B total parameters and about 5.1B active per token, is now available on Vercel's AI Gateway free for three weeks through August 3rd. The …